Heuristic Reward Design for Deep Reinforcement Learning-Based Routing, Modulation and Spectrum Assignment of Elastic Optical Networks

Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach

“…In dynamic scenarios, DRL was applied to solve the routing, modulation, and spectrum assignment (RMSA) problem in single-domain EONs [27,28,30,31], multidomain EONs [32], multiband EONs [33,34] ,and survivable EONs operating under shared protection [35]; the problem of energy-efcient trafc grooming in fog-cloud EONs [36], the problem of establishing and reconfguring multicast sessions in EONs [37], the fragmentation mitigation problem [38], and the resource allocation problem with advanced reservation (AR) in EONs for cloud-edge computing [39]. Only one previous work has studied the application of DRL on MCF networks [40], but this work focused on fxed-grid networks.…”

“…Although rule-based heuristics are computationally simple, their performance depends on the ability of the designer to detect the best set of rules defning the heuristic behavior [26]. In recent years, it has been shown that in most cases, deep reinforcement learning (DRL) techniques applied to solve resource allocation problems in dynamic elastic optical networks outperform rule-based systems [27,28]. DRL has the ability to explore solutions other than those detected by the expert knowledge of the human designer.…”

Busyness level-based deep reinforcement learning method for routing, modulation, and spectrum assignment of elastic optical networks

“…As a result, many heuristic RMSA schemes are proposed [3]. Recently, deep reinforcement learning (DRL) based approaches rise and show advantage over the conventional heuristic methods, thanks to the development of machine learning [4][5][6][7]. Under the DRL framework, the agent observes the EON state, emits a RMSA action and receives a reward from the EON which is to reflect the goodness of the action.…”

“…Since the agent's learning is based on the state it observes and the reward it receives, key information should be carried by the state and the reward. In previous studies [4][5][6][7], however, the observed and feedback information is limited.…”

Intelligent Orchestration Algorithm for Power Backbone Optical Network with Service QoS Awareness

“…As an indispensable part that undertakes the spectrum allocation function in EONs, RSA can set up an optical path for source and destination on the basis of the bandwidth required by power service and allocate continuous spectrum resources. Most of the current researches use static algorithms [10][11][12] , i.e., the service requirements are known, to solve RSA problems. The service traffic from source to destination is also affected by linear and nonlinear physical damage [13] .…”